Using Predicate-Argument Structures for Information Extraction

By Mihai Surdeanu, Sanda M. Harabagiu, John Williams, Paul Aarseth. Annual Meeting of the Association for Computational Linguistics, 2003

462 citations recorded by the source corpus.

In this paper we present a novel, customizable IE paradigm that takes advantage of predicate-argument structures. We also introduce a new way of automatically identifying predicate argument structures, which is central to our IE paradigm. It is based on: (1) an extended set of features; and (2) inductive decision tree learning. The experimental results prove our claim that accurate predicate-argument structures enable high quality IE results.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/18d04fa815cbc9e7a2eeab189a4d7388cb43b0cb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Frame-Semantic Parsing (2014, methodology): “Others have explored the application of frame-semantic structures to tasks such as information extraction (Moschitti, Morarescu, and Harabagiu 2003; Surdeanu et al. 2003), textual entailment (Burchardt and Frank 2006; Burchardt et al.”
Using subcategorization knowledge to improve case prediction for translation to German (2013, unknown): “This basic kind of verb knowledge has been shown to be useful in many NLP tasks such as information extraction (Surdeanu et al., 2003; Venturi1 et al., 2009), parsing (Carroll et al., 1998; Carroll and Fang, 2004) and word sense disambiguation (Kohomban and Lee, 2005; Mc-Carthy et al., 2007).”
Shallow Semantic Parsing using Support Vector Machines (2004, methodology): “SVM 88 Decision Tree (Surdeanu et al., 2003) 79 Gildea and Palmer (2002) 77”
Introduction to the CoNLL-2005 Shared Task: Semantic Role Labeling (2005, methodology): “Looking at the description of the different systems, it becomes clear that the general type of features used in this edition is strongly based on previous work on the SRL task (Gildea and Jurafsky, 2002; Surdeanu et al., 2003; Pradhan et al., 2005a; Xue and Palmer, 2004).”
Semantic Role Chunking Combining Complementary Syntactic Views (2005, background): “They are a combination of features introduced by Gildea and Jurafsky (2002), ones proposed in Pradhan et al. (2004), Surdeanu et al. (2003) and the syntactic-frame feature proposed in (Xue and Palmer, 2004).”
A Joint Sequential and Relational Model for Frame-Semantic Parsing (2017, background): “It has been considered a valuable resource for Natural Language Processing and useful for studying tasks such as information extraction, machine translation, and question answering (Surdeanu et al., 2003; Shen and Lapata, 2007; Liu and Gildea, 2010).”
High-Order Low-Rank Tensors for Semantic Role Labeling (2015, background): “…primarily extended this core set by including local context lexicalized patterns (e.g., n -grams), several extended representations of the path features, and some linguistically motivated syntactic patterns, as the syntactic frame (Surdeanu et al., 2003; Xue and Palmer, 2004; Pradhan et al., 2005).”
Deep Semantic Role Labeling with Self-Attention (2017, background): “…level of semantic representation thus beneﬁting many NLP applications, such as Information Extraction (Bastianelli et al. 2013), Question Answering (Surdeanu et al. 2003; Moschitti, Morarescu, and Harabagiu 2003; Dan and Lapata 2007), Machine Translation (Knight and Luk 1994; Uefﬁng, Haffari, and…”
Special Issue Introduction: Semantic Role Labeling: An Introduction to the Special Issue (2008, unknown): “For instance, Surdeanu et al. (2003) generalized the concept of headword with the content word feature.”
Semi-Supervised Semantic Role Labeling (2009, background): “This is partly due to its relevance for applications ranging from information extraction (Surdeanu et al., 2003; Moschitti et al., 2003) to question answering (Shen and Lapata, 2007), paraphrase identification (Padó and Erk, 2005), and the modeling of textual entailment relations (Tatu and Moldovan,”
End-to-end learning of semantic role labeling using recurrent neural networks (2015, background): “…as an intermediate step in a wide range of natural language processing (NLP) tasks, such as information extraction (Bastianelli et al., 2013), automatic document categorization (Persson et al., 2009) and question-answering (Dan and Lapata, 2007; Surdeanu et al., 2003; Moschitti et al., 2003).”
The Importance of Syntactic Parsing and Inference in Semantic Role Labeling (2008, background): “Some of the early systems are described in (Chen and Rambow, 2003; Gildea and Hockenmaier, 2003; Surdeanu et al., 2003).”
Introduction to the CoNLL-2004 Shared Task: Semantic Role Labeling (2004, methodology): “Regarding the learning component of the systems, we ﬁnd pure probabilistic models (Gildea and Juraf-sky, 2002; Gildea and Palmer, 2002; Gildea and Hock-enmaier, 2003), Maximum Entropy (Fleischman et al., 2003), generative models (Thompson et al., 2003), Decision Trees (Surdeanu et al., 2003; Chen an”